Clarify Confused Nodes via Separated Learning
- URL: http://arxiv.org/abs/2306.02285v3
- Date: Thu, 15 Feb 2024 03:58:01 GMT
- Title: Clarify Confused Nodes via Separated Learning
- Authors: Jiajun Zhou, Shengbo Gong, Chenxuan Xie, Shanqing Yu, Qi Xuan, Xiaoniu
Yang
- Abstract summary: We propose a new metric, termed Neighborhood Confusion, to facilitate a more reliable separation of nodes.
Our framework can effectively separate nodes and yield significant performance improvement compared to the latest methods.
- Score: 4.7653525905230865
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph neural networks (GNNs) have achieved remarkable advances in
graph-oriented tasks. However, real-world graphs invariably contain a certain
proportion of heterophilous nodes, challenging the homophily assumption of
classical GNNs and hindering their performance. Most existing studies continue
to design generic models with shared weights between heterophilous and
homophilous nodes. Despite the incorporation of high-order messages or
multi-channel architectures, these efforts often fall short. A minority of
studies attempt to train different node groups separately but suffer from
inappropriate separation metrics and low efficiency. In this paper, we first
propose a new metric, termed Neighborhood Confusion (NC), to facilitate a more
reliable separation of nodes. We observe that node groups with different levels
of NC values exhibit certain differences in intra-group accuracy and visualized
embeddings. These pave the way for Neighborhood Confusion-guided Graph
Convolutional Network (NCGCN), in which nodes are grouped by their NC values
and accept intra-group weight sharing and message passing. Extensive
experiments on both homophilous and heterophilous benchmarks demonstrate that
our framework can effectively separate nodes and yield significant performance
improvement compared to the latest methods. The source code will be released
soon.
Related papers
- The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs [59.03660013787925]
We introduce the Heterophily Snowflake Hypothesis and provide an effective solution to guide and facilitate research on heterophilic graphs.
Our observations show that our framework acts as a versatile operator for diverse tasks.
It can be integrated into various GNN frameworks, boosting performance in-depth and offering an explainable approach to choosing the optimal network depth.
arXiv Detail & Related papers (2024-06-18T12:16:00Z) - Demystifying Structural Disparity in Graph Neural Networks: Can One Size
Fit All? [61.35457647107439]
Most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns.
We provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes.
We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity.
arXiv Detail & Related papers (2023-06-02T07:46:20Z) - When Do Graph Neural Networks Help with Node Classification?
Investigating the Impact of Homophily Principle on Node Distinguishability [92.8279562472538]
Homophily principle has been believed to be the main reason for the performance superiority of Graph Networks (GNNs) over Neural Networks on node classification tasks.
Recent research suggests that, even in the absence of homophily, the advantage of GNNs still exists as long as nodes from the same class share similar neighborhood patterns.
arXiv Detail & Related papers (2023-04-25T09:40:47Z) - GCNH: A Simple Method For Representation Learning On Heterophilous
Graphs [4.051099980410583]
Graph Neural Networks (GNNs) are well-suited for learning on homophilous graphs.
Recent works have proposed extensions to standard GNN architectures to improve performance on heterophilous graphs.
We propose GCN for Heterophily (GCNH), a simple yet effective GNN architecture applicable to both heterophilous and homophilous scenarios.
arXiv Detail & Related papers (2023-04-21T11:26:24Z) - Revisiting Heterophily For Graph Neural Networks [42.41238892727136]
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption)
Recent work has identified a non-trivial set of datasets where their performance compared to NNs is not satisfactory.
arXiv Detail & Related papers (2022-10-14T08:00:26Z) - Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with
Heterophily [58.76759997223951]
We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs.
We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
arXiv Detail & Related papers (2022-03-19T14:26:43Z) - Graph Neural Networks with Feature and Structure Aware Random Walk [5.431036185361236]
We show that in typical heterphilous graphs, the edges may be directed, and whether to treat the edges as is or simply make them undirected greatly affects the performance of the GNN models.
We develop a model that adaptively learns the directionality of the graph, and exploits the underlying long-distance correlations between nodes.
arXiv Detail & Related papers (2021-11-19T08:54:21Z) - Is Homophily a Necessity for Graph Neural Networks? [50.959340355849896]
Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks.
GNNs are widely believed to work well due to the homophily assumption ("like attracts like"), and fail to generalize to heterophilous graphs where dissimilar nodes connect.
Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion.
In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than
arXiv Detail & Related papers (2021-06-11T02:44:00Z) - Graph Neural Networks with Heterophily [40.23690407583509]
We propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily.
We show that replacing the compatibility matrix in our framework with the identity (which represents pure homophily) reduces to GCN.
arXiv Detail & Related papers (2020-09-28T18:29:36Z) - Towards Deeper Graph Neural Networks with Differentiable Group
Normalization [61.20639338417576]
Graph neural networks (GNNs) learn the representation of a node by aggregating its neighbors.
Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases.
We introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN)
arXiv Detail & Related papers (2020-06-12T07:18:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.